Traditional AI
The increasing level of automation in manufacturing also requires the automation of material and plant testing with as little human intervention as possible. In order to remain competitive while meeting industry standards, companies strive to achieve both quantity and quality in production without having to make compromises. However, manual quality testing of workpieces usually only allows the analysis of individual samples from a specific product series. In addition, planned predictive maintenance of machines can either result in unnecessary downtime if done too early or, if performed too late, unexpected equipment failure. For this purpose, predictive maintenance based on machine learning was developed, which helps to determine and monitor the condition of workpieces, machine components and process flows, to predict ideal maintenance plans and to recommend appropriate measures.
One way that allows companies of all sizes to use the latest advances in machine learning-based applications for predictive maintenance is to integrate them with mobile IoT sensors powered by cloud technology. This allows easy, non-invasive prototyping and experimentation, and the provision of a full condition monitoring service at a reasonable cost. Amazon Monitron, which is offered by Amazon Web Services (AWS), is an easy-to-set up cloud-based condition monitoring solution. Monitron's mobile IoT sensors are attached to your machines to collect vibration and temperature data from machine components such as bearings, gears, motors, or pumps. The collected sensor data is sent to AWS for storage and analysis via a Monitron gateway connected to your WiFi network. In order to ensure a maximum level of security and to guarantee the security of your data, the data is also continuously encrypted.
The following architecture diagram illustrates a more detailed use case for analyzing and visualizing incoming sensor data using Amazon cloud-based technologies. Amazon Monitron sensors measure and detect abnormalities from your machine components. Both measurement data and machine-learning-based anomaly detection are collected by AWS services (Kinesis Streams and Firehose) and stored in Amazon S3. AWS Glue crawlers analyze Amazon Monitron data in Amazon S3, create metadata schemas and tables in Athena. Finally, Grafana uses Athena to query Amazon S3 data, which enables the creation of easy-to-use dashboards for convenient visualization of measurement data and machine status.
In summary, with the advent of huge improvements in artificial intelligence and cloud technologies, companies like yours can start to benefit from these technologies and use them during the production cycle to automate quality testing and monitor machine health in a cost-effective way, minimizing human intervention and optimizing factory capacities. To put it in the words of chess grandmaster Garri Kasparov, who lost to the IBM computer “Deep Blue” in 1997: “Man plus machine means finding a better way to combine better interfaces and better processes.”
In our latest article, we highlight the central role of compliance and quality management in the development of AI systems. We show how innovative approaches can be reconciled with regulatory requirements — an important step for companies that want to drive sustainable innovations in the fast-moving world of technology.
Discover the impact of generative AI in retail. This technology unites departments, personalises content, and transforms customer experiences. Leading brands such as Coca-Cola and Walmart are already using their potential to optimise operations and drive innovation. Explore the future of retail with generative AI...
This article explores how large language models such as ChatGPT can be integrated with proprietary data. The recent advent of large language models opens up numerous opportunities for companies, but connecting with proprietary data is a challenge in such a transformation. This article discusses the various approaches to solve this problem, such as fine-tuning and contextual learning. In addition, the associated challenges and risks are addressed.
